© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101166
    Prev
    Next
    INDEX
    Explanations

    biological research terms

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects the word "biological" and related scientific terms, particularly in scientific or medical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -3.03
     verdaderamente
    -2.86
     sorprend
    -2.47
     soñ
    -2.34
     extremadamente
    -2.30
     سواء
    -2.28
     بالإضافة
    -2.27
     suced
    -2.27
     pembun
    -2.25
     aparentemente
    -2.17
    POSITIVE LOGITS
    ၟ
    3.23
    .
    2.89
    呖
    2.83
    !”
    2.66
    </h3>
    2.59
    o
    2.52
     さま
    2.47
    
    2.47
    ли
    2.45
    猻
    2.44
    Activations Density 0.015%

    No Known Activations